granite.build: Skill for Claude Code

.claude/skills/gb-docs/SKILL.md

gb-docs is a skill for Claude Code from ibm-granite/granite.build. It costs 59 tokens per session (1,215 once invoked), scanned A, original, Apache-2.0.

A documentation lookup skill for Granite.build, a build system with configuration files, command-line tools, and different execution backends. It reads the project's bundled Markdown documentation and cites the relevant file.

In plain words
What is it for?
It helps answer questions about Granite.build schemas, inputs and outputs, URIs, steps, troubleshooting, and backend-specific behaviour.
Why use it?
It reduces guesswork about configuration fields, commands, errors, and which documented features work with the current Bash backend rather than Kubernetes or LSF.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is ibm-granite/granite.build's own configuration. It tells Claude Code how to work on granite.build itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything granite.build configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ibm-granite/granite.build. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ibm-granite/granite.build/main/.claude/skills/gb-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ibm-granite/granite.build

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gb-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/ibm-granite/granite.build/gb-docs.svg)](https://agentmods.dev/skills/ibm-granite/granite.build/gb-docs)
Your own site
<a href="https://agentmods.dev/skills/ibm-granite/granite.build/gb-docs"><img src="https://agentmods.dev/badge/skills/ibm-granite/granite.build/gb-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01215
Opus 5 $0.00030 $0.00607
Sonnet 5 $0.00012 $0.00243
Haiku 4.5 $0.00006 $0.00121

Measured 3d ago against content hash b00089a66451, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gb-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/gb-docs/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Granite.build docs lookup

Granite.build's docs ship as Markdown in references/ next to this skill. Read the relevant file(s) with the file tools, then answer grounded in their content, citing the doc path.

Pick a file from the topic index below and read it directly with the file tools.

Important caveat: the docs are k8s/LSF-centric

This environment runs the standalone bash backend by default, but most docs are written for the Kubernetes/LSF backends. Several documented conveniences do not apply to bash, e.g.:

  • config.workload.commands (inline command list) — k8s/LSF only.
  • config.gb.files_to_create / additional_files — k8s/LSF only.
  • The generic gbstep step — has no bash launcher; using it on bash fails with KeyError: 'helm'.

So: use the docs for the schema and concepts (URIs, inputs/outputs, the field reference), but for how a bash step actually launches and behaves, prefer these over the doc prose:

  • The create-build skill's references/steps.md — tested contracts (inputs/outputs/env, the artifact monitor) for the shipped bash steps (inference, lora-finetune, inference-lora, hello, command).
  • A prior successful build's job.log, via build_job_log — the real stdout of a working build. Reverse-engineering a working build beats guessing from docs.

When the docs and actual bash behavior disagree, trust the observed behavior and say so.

Where the docs are

Everything is in references/ next to this SKILL.md (the index below lists references/<x> paths). If a file is ever missing locally, the same docs are online in the ibm-granite/granite.build repository.

Index — pick by topic

Authoring builds

  • references/builds/build-yaml-reference.mdauthoritative build.yaml schema (targets, steps, inputs/outputs, URIs, all fields/options).
  • references/builds/README.md — build features overview; references/builds/hf-push.md — push artifacts to HuggingFace; references/builds/event-notifications.md.
  • references/steps/bring-your-own-step.md, references/steps/custom-code-steps.md, references/steps/bring-your-own-image.md — author/use custom steps (examples lean k8s/docker; the commands/files_to_create features are k8s/LSF only). references/steps/README.md — steps overview.

Read the full file on GitHub · 63 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 63 lines · 59 tokens per session scan A b00089a66451

Subscribe to this mod's changes

gb-docs is a skill published in the GitHub repository ibm-granite/granite.build (44 stars, last pushed 3d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,215 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens